Analytics Model

from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import adjusted_rand_score
eda = pd.read_parquet("data/eda.parquet")

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
Cell In[1], line 8
      6 from sklearn.preprocessing import LabelEncoder
      7 from sklearn.metrics import adjusted_rand_score
----> 8 eda = pd.read_parquet("data/eda.parquet")

File /opt/hostedtoolcache/Python/3.11.12/x64/lib/python3.11/site-packages/pandas/io/parquet.py:651, in read_parquet(path, engine, columns, storage_options, use_nullable_dtypes, dtype_backend, filesystem, filters, **kwargs)
    498 @doc(storage_options=_shared_docs["storage_options"])
    499 def read_parquet(
    500     path: FilePath | ReadBuffer[bytes],
   (...)
    508     **kwargs,
    509 ) -> DataFrame:
    510     """
    511     Load a parquet object from the file path, returning a DataFrame.
    512 
   (...)
    648     1    4    9
    649     """
--> 651     impl = get_engine(engine)
    653     if use_nullable_dtypes is not lib.no_default:
    654         msg = (
    655             "The argument 'use_nullable_dtypes' is deprecated and will be removed "
    656             "in a future version."
    657         )

File /opt/hostedtoolcache/Python/3.11.12/x64/lib/python3.11/site-packages/pandas/io/parquet.py:67, in get_engine(engine)
     64         except ImportError as err:
     65             error_msgs += "\n - " + str(err)
---> 67     raise ImportError(
     68         "Unable to find a usable engine; "
     69         "tried using: 'pyarrow', 'fastparquet'.\n"
     70         "A suitable version of "
     71         "pyarrow or fastparquet is required for parquet "
     72         "support.\n"
     73         "Trying to import the above resulted in these errors:"
     74         f"{error_msgs}"
     75     )
     77 if engine == "pyarrow":
     78     return PyArrowImpl()

ImportError: Unable to find a usable engine; tried using: 'pyarrow', 'fastparquet'.
A suitable version of pyarrow or fastparquet is required for parquet support.
Trying to import the above resulted in these errors:
 - Missing optional dependency 'pyarrow'. pyarrow is required for parquet support. Use pip or conda to install pyarrow.
 - Missing optional dependency 'fastparquet'. fastparquet is required for parquet support. Use pip or conda to install fastparquet.

features = eda[['SALARY', 'MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE']].copy()

for col in ['MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE', 'SALARY']:
    features[col] = pd.to_numeric(features[col], errors='coerce')

features = features.dropna()

scaler = StandardScaler()
X = scaler.fit_transform(features)

kmeans = KMeans(n_clusters=4, random_state=688)
eda.loc[features.index, 'Cluster'] = kmeans.fit_predict(X)

true_labels = eda.loc[features.index, 'SOC_2021_4_NAME']
true_labels_encoded = LabelEncoder().fit_transform(true_labels)

ari = adjusted_rand_score(true_labels_encoded, eda.loc[features.index, 'Cluster'])

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[2], line 1
----> 1 features = eda[['SALARY', 'MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE']].copy()
      3 for col in ['MAX_YEARS_EXPERIENCE', 'MIN_YEARS_EXPERIENCE', 'SALARY']:
      4     features[col] = pd.to_numeric(features[col], errors='coerce')

NameError: name 'eda' is not defined

import plotly.express as px
import plotly.graph_objects as go
from IPython.display import HTML

# 1) Build the DataFrame
df_plot = features.copy()
df_plot['Cluster'] = eda.loc[features.index, 'Cluster']

# 2) Compute centroids in original units
centroids = kmeans.cluster_centers_
centroids_x = centroids[:, 0] * X.std(axis=0)[0] + X.mean(axis=0)[0]
centroids_y = centroids[:, 1] * X.std(axis=0)[1] + X.mean(axis=0)[1]

# 3) Create an interactive Plotly Figure
fig = px.scatter(
    df_plot,
    x='SALARY',
    y='MAX_YEARS_EXPERIENCE',
    color='Cluster',
    title="KMeans Clustering by Salary and Max Years Experience",
    labels={
        'SALARY': 'Salary',
        'MAX_YEARS_EXPERIENCE': 'Max Years Experience',
        'Cluster': 'Cluster'
    },
    width=800,
    height=500,
)

# 4) Add centroid traces
fig.add_trace(
    go.Scatter(
        x=centroids_x,
        y=centroids_y,
        mode='markers',
        marker=dict(symbol='x', size=18, color='black', line=dict(width=2, color='white')),
        name='Centroids'
    )
)

fig.write_html(
    "figures/analytics_plot1.html",
    include_plotlyjs="cdn",
    full_html=True
)
fig

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[3], line 6
      3 from IPython.display import HTML
      5 # 1) Build the DataFrame
----> 6 df_plot = features.copy()
      7 df_plot['Cluster'] = eda.loc[features.index, 'Cluster']
      9 # 2) Compute centroids in original units

NameError: name 'features' is not defined

Here we have 4 cluster groups. Group 0, which represent as green have lower salary, mostly under 150k, and max years experience in 2-5 years, it is likely Likely junior to mid-level employees with moderate pay. Group 1 with orange, has medium to high salary, wide range from $100k–$500k and with narrow range ~3 years, they are suggests specialized or high-paying roles with short experience — possibly fast-track promotions or high-demand fields. cluster 2 are low salary and experience from 0-4 years, they are clearly entry level employee. cluster 3 has medium salary, mostly under 200k with higher experiences, like 6-13 eyars. They probably are senior professionals with more experience but not the highest salaries.

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score
import plotly.graph_objects as go

# Prepare features & target
features = eda[['MIN_YEARS_EXPERIENCE', 'MAX_YEARS_EXPERIENCE']].apply(pd.to_numeric, errors='coerce')
features = features.dropna()
X = features
y = eda.loc[X.index, 'SALARY']

# Train/test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=688)

# Fit model & predict
model = LinearRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

# Metrics (optional, but handy)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
print(f"MSE: {mse:.2f}, R²: {r2:.3f}")

# Define min/max for the identity line
min_val = y_test.min()
max_val = y_test.max()

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[4], line 8
      5 import plotly.graph_objects as go
      7 # Prepare features & target
----> 8 features = eda[['MIN_YEARS_EXPERIENCE', 'MAX_YEARS_EXPERIENCE']].apply(pd.to_numeric, errors='coerce')
      9 features = features.dropna()
     10 X = features

NameError: name 'eda' is not defined

fig = go.Figure([
    go.Scatter(
        x=y_test,
        y=y_pred,
        mode='markers',
        marker=dict(color='skyblue', opacity=0.6),
        name='Predicted vs Actual'
    ),
    go.Scatter(
        x=[min_val, max_val],
        y=[min_val, max_val],
        mode='lines',
        line=dict(color='red', dash='dash'),
        name='Ideal Fit'
    )
])

fig.update_layout(
    title='Actual vs Predicted Salary (Multiple Regression)',
    xaxis_title='Actual Salary',
    yaxis_title='Predicted Salary',
    width=800,
    height=600,
    template='plotly_white'
)


fig.write_html(
    'figures/analytics_plot2.html',
    include_plotlyjs='cdn',
    full_html=False
)
fig

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[5], line 3
      1 fig = go.Figure([
      2     go.Scatter(
----> 3         x=y_test,
      4         y=y_pred,
      5         mode='markers',
      6         marker=dict(color='skyblue', opacity=0.6),
      7         name='Predicted vs Actual'
      8     ),
      9     go.Scatter(
     10         x=[min_val, max_val],
     11         y=[min_val, max_val],
     12         mode='lines',
     13         line=dict(color='red', dash='dash'),
     14         name='Ideal Fit'
     15     )
     16 ])
     18 fig.update_layout(
     19     title='Actual vs Predicted Salary (Multiple Regression)',
     20     xaxis_title='Actual Salary',
   (...)
     24     template='plotly_white'
     25 )
     28 fig.write_html(
     29     'figures/analytics_plot2.html',
     30     include_plotlyjs='cdn',
     31     full_html=False
     32 )

NameError: name 'y_test' is not defined

This plot shows the Actual vs. Predicted Salary using a multiple linear regression model. The blue dots represent individual predictions, and the red dashed line is the ideal line where predicted = actual. Since most points lie very close to the red line, it means your model predicts salary very accurately, with minimal error and strong linear fit — likely reflected in a high R² score near 1.0.